SGD with greedy step size on smooth quadratics in the interpolation regime attains O(1/t^{3/4}) last-iterate convergence.
Optimal rates in continual linear regression via increasing regularization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
SGD with greedy step size on smooth quadratics in the interpolation regime attains O(1/t^{3/4}) last-iterate convergence.
- PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks